Abstract
Many applications use recommender systems to predict user preferences, improve user experience, and increase the amount of sales. However, because of the cold-start problem, it is not easy to recommend items to new users accurately. Recommendation performance degrades in the case of users with little interaction, in particular latent users who have never used the service. To alleviate the cold-start problem, we develop a framework that combines an online shopping domain with information from an Ads platform. Our framework employs deep learning to build a cross-domain recommender system based on shared users in these two domains. This is the first attempt that models users based on shared users in online shopping and Ads domains for solving the user-cold start problem. We apply Word2Vec to turn textual information on users and items into latent vectors as their representations. The experimental results show the effectiveness of deep neural approaches with knowledge transferred from another domain for the cold-start problem. Textual information may contain useless information, and Word2Vec cannot capture some structural and semantic correlations between different users. Therefore, we propose R-metapath2Vec to enhance user modeling and use the Stacking model to integrate these two kinds of user representations. The experimental results demonstrate the effectiveness of our integration model: our framework can recommend products to users of another domain through Ads distribution in a more accurate level.
Highlights
It is hard for online shopping users to explore more than thousands items and make a better choice from them in a limited time
The items in our online shopping domain exist in a short period of time, and we found that there are on average about 1,500 items for sale per day from 5-11-2017 to 9-10-2017
The performance of a ranked list was evaluated by Hit Ratio (HR) and Normalized Discounted Cumulative Gain (NDCG) [33]
Summary
It is hard for online shopping users to explore more than thousands items and make a better choice from them in a limited time. Some recent works have applied deep neural networks (DNNs) to recommendation tasks With their powerful abilities to model a high level of non-linearity, [5] and [6] proposed methods that leverage a multi-layer feed-forward neural network to learn the user-item interaction function. Several works [1], [13] integrated graph embedding methods and side information (e.g. categories of items, brands of items) to improve recommendation performance and alleviate the cold-start problem. For modeling the user-item interaction function in the online shopping domain, we train a deep neural model based on bridge users’ purchase records to improve the recommendation performance for new users with sufficient browsing records in the Ads domain.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
More From: IEEE Open Journal of the Industrial Electronics Society
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.